# Cursor

# Step 1. Open Cursor Settings

In Cursor, open Settings and go to the Models tab. Scroll down to the API Keys section.

# Step 2. Add Your PHOENIQS API Key

Paste your PHOENIQS API Key into the OpenAI API Key field, then set Override OpenAI Base URL to:

https://maas.phoeniqs.com/v1

Make sure both toggles are enabled (green).

# Step 3. Add Your Model

At the bottom of the model list click on "Add a model". Get the exact model name from the PHOENIQS Active Models list. For example:

inference-apertus-70b
inference-gpt-oss-120b
inference-glm5

Recommended: Use inference-glm5 for the best Cursor experience. GLM 5 is optimized for agentic engineering and long-horizon coding, and is the only model that fully supports Agent, Chat, and Plan modes in Cursor.

Paste the name into Cursor and enable the toggle for the newly added model.

# Step 4. Test It

Open Ask mode with Cmd+L / Ctrl+L and select your model.

Send a message. All requests now route through your PHOENIQS API, which uses our sovereign GPUs hosted in Switzerland.

# Troubleshooting

Issue	Solution
Model not responding	Check base URL ends with `/v1` and key has model access
Auth errors	Regenerate key; ensure it starts with `sk-`
Agent mode not working	Use `inference-glm5`; other models only support Ask and Plan modes

maas integrations cursor